From 2eece58c272bd58a089ec5f897f3705b8115deb8 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Sun, 2 Feb 2025 04:00:47 -0800 Subject: [PATCH] Update llama.py --- unsloth/models/llama.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index d0ffa53d5b..97a1fc2335 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -936,13 +936,12 @@ def LlamaModel_fast_forward_inference( next_decoder_cache = [] residual = torch.empty_like(X) - print(bsz, q_len, hd) _XX = torch.empty((2, bsz, q_len, hd), dtype = torch.float32, device = "cuda:0") XX, XX2 = _XX[0], _XX[1] variance = torch.empty((bsz, q_len, 1), dtype = torch.float32, device = "cuda:0") temp_mlp = torch.empty((2, bsz, 1, mlp_size), dtype = X.dtype, device = "cuda:0") temp_gate, temp_up = temp_mlp[0], temp_mlp[1] - + for idx, decoder_layer in enumerate(self.model.layers): residual.copy_(X) # residual = X X = fast_rms_layernorm_inference(